nvidia/Llama-3_3-Nemotron-Super-49B-GenRM
Text Generation
•
50B
•
Updated
•
15
•
4
Reward Models
Nemotron reward models. For use in RLHF pipelines and LLM-as-a-Judge
-
-
nvidia/Llama-3_3-Nemotron-Super-49B-GenRM-Multilingual
Text Generation • 50B • Updated • 16 • 5 -
nvidia/Llama-3.3-Nemotron-70B-Reward
Text Generation • 71B • Updated • 11 • 2 -
nvidia/Llama-3.3-Nemotron-70B-Reward-Multilingual
Text Generation • 71B • Updated • 23 • 3 -
nvidia/Qwen-2.5-Nemotron-32B-Reward
Text Classification • 32B • Updated • 9 • 1 -
nvidia/Qwen-3-Nemotron-32B-Reward
Text Classification • 32B • Updated • 11 • 3 -
HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages
Paper • 2505.11475 • Published • 3 -
nvidia/HelpSteer3
Viewer • Updated • 99k • 2.36k • 54